NeuroKoop: Neural Koopman Fusion of Structural-Functional Connectomes for Identifying Prenatal Drug Exposure in Adolescents
This work addresses the problem of improving predictive performance for prenatal drug exposure in adolescents, offering a domain-specific incremental advance in neuroimaging analysis.
The paper tackled the challenge of identifying prenatal drug exposure in adolescents by integrating structural and functional brain connectomes, introducing NeuroKoop, a graph neural network framework that outperformed baselines on the ABCD dataset.
Understanding how prenatal exposure to psychoactive substances such as cannabis shapes adolescent brain organization remains a critical challenge, complicated by the complexity of multimodal neuroimaging data and the limitations of conventional analytic methods. Existing approaches often fail to fully capture the complementary features embedded within structural and functional connectomes, constraining both biological insight and predictive performance. To address this, we introduced NeuroKoop, a novel graph neural network-based framework that integrates structural and functional brain networks utilizing neural Koopman operator-driven latent space fusion. By leveraging Koopman theory, NeuroKoop unifies node embeddings derived from source-based morphometry (SBM) and functional network connectivity (FNC) based brain graphs, resulting in enhanced representation learning and more robust classification of prenatal drug exposure (PDE) status. Applied to a large adolescent cohort from the ABCD dataset, NeuroKoop outperformed relevant baselines and revealed salient structural-functional connections, advancing our understanding of the neurodevelopmental impact of PDE.